Adding Evaluation Results (#1)

- Adding Evaluation Results (33f8e576f5c4d826dc4dc0f3af931836fdcb6f69)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,14 +1,117 @@
 ---
-base_model:
-- SanjiWatsuki/Kunoichi-DPO-v2-7B
-- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
-tags:
-- mergekit
-- merge
-license: cc-by-nc-4.0
 language:
 - en
+license: cc-by-nc-4.0
 library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- SanjiWatsuki/Kunoichi-DPO-v2-7B
+- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
+model-index:
+- name: finch
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 71.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 87.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 67.96
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 84.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
+      name: Open LLM Leaderboard
 ---
 
 ![Finch](https://i.imgur.com/Da14544.gif)
@@ -46,4 +149,17 @@ slices:
     model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
   - layer_range: [0, 32]
     model: SanjiWatsuki/Kunoichi-DPO-v2-7B
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_antiven0m__finch)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.78|
+|AI2 Reasoning Challenge (25-Shot)|71.59|
+|HellaSwag (10-Shot)              |87.87|
+|MMLU (5-Shot)                    |64.81|
+|TruthfulQA (0-shot)              |67.96|
+|Winogrande (5-shot)              |84.14|
+|GSM8k (5-shot)                   |66.34|
+